AutoML Leaderboard

Best model	name	model_type	metric_type	metric_value	train_time
	1_Baseline	Baseline	auc	0.5	0.91
	2_DecisionTree	Decision Tree	auc	0.517821	6.65
the best	3_Linear	Linear	auc	0.603392	3.2
	4_Default_Xgboost	Xgboost	auc	0.551788	26.29
	5_Default_NeuralNetwork	Neural Network	auc	0.563967	2.64
	6_Default_RandomForest	Random Forest	auc	0.558326	7.23
	Ensemble	Ensemble	auc	0.603392	0.51

AutoML Performance

AutoML Performance Boxplot

Features Importance

Spearman Correlation of Models

Summary of 5_Default_NeuralNetwork

<< Go back

Neural Network

• n_jobs: -1
• dense_1_size: 32
• dense_2_size: 16
• learning_rate: 0.05
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

1.8 seconds

Metric details

	score	threshold
logloss	0.76868	nan
auc	0.563967	nan
f1	0.651564	0.00190441
accuracy	0.5576	0.426766
precision	0.59322	0.888019
recall	1	0.00190441
mcc	0.112859	0.426766

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.76868	nan
auc	0.563967	nan
f1	0.530161	0.426766
accuracy	0.5576	0.426766
precision	0.544503	0.426766
recall	0.516556	0.426766
mcc	0.112859	0.426766

Confusion matrix (at threshold=0.426766)

	Predicted as 0	Predicted as 1
Labeled as 0	385	261
Labeled as 1	292	312

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

<< Go back

Summary of 1_Baseline

<< Go back

Baseline Classifier (Baseline)

• n_jobs: -1
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

0.2 seconds

Metric details

	score	threshold
logloss	0.692583	nan
auc	0.5	nan
f1	0.651564	0.43488
accuracy	0.4832	0.43488
precision	0.4832	0.43488
recall	1	0.43488
mcc	0	0.43488

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.692583	nan
auc	0.5	nan
f1	0.651564	0.43488
accuracy	0.4832	0.43488
precision	0.4832	0.43488
recall	1	0.43488
mcc	0	0.43488

Confusion matrix (at threshold=0.43488)

	Predicted as 0	Predicted as 1
Labeled as 0	0	646
Labeled as 1	0	604

Learning curves

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

<< Go back

Summary of Ensemble

<< Go back

Ensemble structure

Model	Weight
3_Linear	1

Metric details

	score	threshold
logloss	0.682999	nan
auc	0.603392	nan
f1	0.661972	0.316161
accuracy	0.5776	0.451899
precision	0.613333	0.721944
recall	1	0.101465
mcc	0.194736	0.381235

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.682999	nan
auc	0.603392	nan
f1	0.609467	0.451899
accuracy	0.5776	0.451899
precision	0.550802	0.451899
recall	0.682119	0.451899
mcc	0.165133	0.451899

Confusion matrix (at threshold=0.451899)

	Predicted as 0	Predicted as 1
Labeled as 0	310	336
Labeled as 1	192	412

Learning curves

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

<< Go back

Summary of 2_DecisionTree

<< Go back

Decision Tree

• n_jobs: -1
• criterion: gini
• max_depth: 3
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

5.7 seconds

Metric details

	score	threshold
logloss	0.700574	nan
auc	0.517821	nan
f1	0.651564	0.366983
accuracy	0.5288	0.500811
precision	0.51928	0.500811
recall	1	0.366983
mcc	0.0485308	0.500811

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.700574	nan
auc	0.517821	nan
f1	0.406848	0.500811
accuracy	0.5288	0.500811
precision	0.51928	0.500811
recall	0.334437	0.500811
mcc	0.0485308	0.500811

Confusion matrix (at threshold=0.500811)

	Predicted as 0	Predicted as 1
Labeled as 0	459	187
Labeled as 1	402	202

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

SHAP Importance

<< Go back

Summary of 6_Default_RandomForest

<< Go back

Random Forest

• n_jobs: -1
• criterion: gini
• max_features: 0.9
• min_samples_split: 30
• max_depth: 4
• eval_metric_name: auc
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

6.3 seconds

Metric details

	score	threshold
logloss	0.689063	nan
auc	0.558326	nan
f1	0.656683	0.414255
accuracy	0.5552	0.490009
precision	0.549793	0.490009
recall	1	0.3158
mcc	0.12066	0.46638

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.689063	nan
auc	0.558326	nan
f1	0.488029	0.490009
accuracy	0.5552	0.490009
precision	0.549793	0.490009
recall	0.438742	0.490009
mcc	0.105571	0.490009

Confusion matrix (at threshold=0.490009)

	Predicted as 0	Predicted as 1
Labeled as 0	429	217
Labeled as 1	339	265

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

SHAP Importance

<< Go back

Summary of 4_Default_Xgboost

<< Go back

Extreme Gradient Boosting (Xgboost)

• n_jobs: -1
• objective: binary:logistic
• eta: 0.075
• max_depth: 6
• min_child_weight: 1
• subsample: 1.0
• colsample_bytree: 1.0
• eval_metric: auc
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

25.3 seconds

Metric details

	score	threshold
logloss	0.698165	nan
auc	0.551788	nan
f1	0.651564	0.166114
accuracy	0.5472	0.438415
precision	0.537415	0.520788
recall	1	0.166114
mcc	0.110456	0.438415

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.698165	nan
auc	0.551788	nan
f1	0.602528	0.438415
accuracy	0.5472	0.438415
precision	0.523171	0.438415
recall	0.710265	0.438415
mcc	0.110456	0.438415

Confusion matrix (at threshold=0.438415)

	Predicted as 0	Predicted as 1
Labeled as 0	255	391
Labeled as 1	175	429

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

SHAP Importance

<< Go back

Summary of 3_Linear

<< Go back

Logistic Regression (Linear)

• n_jobs: -1
• explain_level: 2

Validation

• validation_type: split
• train_ratio: 0.75
• shuffle: True
• stratify: True

Optimized metric

auc

Training time

2.2 seconds

Metric details

	score	threshold
logloss	0.682999	nan
auc	0.603392	nan
f1	0.661972	0.316161
accuracy	0.5776	0.451899
precision	0.613333	0.721944
recall	1	0.101465
mcc	0.194736	0.381235

Metric details with threshold from accuracy metric

	score	threshold
logloss	0.682999	nan
auc	0.603392	nan
f1	0.609467	0.451899
accuracy	0.5776	0.451899
precision	0.550802	0.451899
recall	0.682119	0.451899
mcc	0.165133	0.451899

Confusion matrix (at threshold=0.451899)

	Predicted as 0	Predicted as 1
Labeled as 0	310	336
Labeled as 1	192	412

Learning curves

Permutation-based Importance

Confusion Matrix

Normalized Confusion Matrix

ROC Curve

Kolmogorov-Smirnov Statistic

Precision-Recall Curve

Calibration Curve

Cumulative Gains Curve

Lift Curve

SHAP Importance

<< Go back